{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F623JQ2RD3CPF3RCEFYWWDFGDA","short_pith_number":"pith:F623JQ2R","schema_version":"1.0","canonical_sha256":"2fb5b4c3511ec4f2ee2221716b0ca618006f87893bc6d3ef3abecc4381352e93","source":{"kind":"arxiv","id":"2505.19605","version":1},"attestation_state":"computed","paper":{"title":"Kuramoto-FedAvg: Using Synchronization Dynamics to Improve Federated Learning Optimization under Statistical Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aggrey Muhebwa, Fatima Anwar, Khalid K. Osman, Khotso Selialia","submitted_at":"2025-05-26T07:16:00Z","abstract_excerpt":"Federated learning on heterogeneous (non-IID) client data experiences slow convergence due to client drift. To address this challenge, we propose Kuramoto-FedAvg, a federated optimization algorithm that reframes the weight aggregation step as a synchronization problem inspired by the Kuramoto model of coupled oscillators. The server dynamically weighs each client's update based on its phase alignment with the global update, amplifying contributions that align with the global gradient direction while minimizing the impact of updates that are out of phase. We theoretically prove that this synchr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.19605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T07:16:00Z","cross_cats_sorted":[],"title_canon_sha256":"c45ab21e2136989fed15ead5735c2fc31232b83af619f05dd1721d483eb1b469","abstract_canon_sha256":"0314fcb2bf3a66d82c8d3cec60925b8cc85f76e816891ca81653b8101424ed01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:33.386877Z","signature_b64":"LeRCixmmvoAi5jaNKl0gBm1m8GalM9PL+E1T4rxD4KXjs38gxe1lSRZN6tHzGnEGgSts8CRwKpbh9ymHqHGRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fb5b4c3511ec4f2ee2221716b0ca618006f87893bc6d3ef3abecc4381352e93","last_reissued_at":"2026-07-05T11:09:33.386418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:33.386418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kuramoto-FedAvg: Using Synchronization Dynamics to Improve Federated Learning Optimization under Statistical Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aggrey Muhebwa, Fatima Anwar, Khalid K. Osman, Khotso Selialia","submitted_at":"2025-05-26T07:16:00Z","abstract_excerpt":"Federated learning on heterogeneous (non-IID) client data experiences slow convergence due to client drift. To address this challenge, we propose Kuramoto-FedAvg, a federated optimization algorithm that reframes the weight aggregation step as a synchronization problem inspired by the Kuramoto model of coupled oscillators. The server dynamically weighs each client's update based on its phase alignment with the global update, amplifying contributions that align with the global gradient direction while minimizing the impact of updates that are out of phase. We theoretically prove that this synchr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19605","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.19605/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.19605","created_at":"2026-07-05T11:09:33.386471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19605v1","created_at":"2026-07-05T11:09:33.386471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19605","created_at":"2026-07-05T11:09:33.386471+00:00"},{"alias_kind":"pith_short_12","alias_value":"F623JQ2RD3CP","created_at":"2026-07-05T11:09:33.386471+00:00"},{"alias_kind":"pith_short_16","alias_value":"F623JQ2RD3CPF3RC","created_at":"2026-07-05T11:09:33.386471+00:00"},{"alias_kind":"pith_short_8","alias_value":"F623JQ2R","created_at":"2026-07-05T11:09:33.386471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA","json":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA.json","graph_json":"https://pith.science/api/pith-number/F623JQ2RD3CPF3RCEFYWWDFGDA/graph.json","events_json":"https://pith.science/api/pith-number/F623JQ2RD3CPF3RCEFYWWDFGDA/events.json","paper":"https://pith.science/paper/F623JQ2R"},"agent_actions":{"view_html":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA","download_json":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA.json","view_paper":"https://pith.science/paper/F623JQ2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19605&json=true","fetch_graph":"https://pith.science/api/pith-number/F623JQ2RD3CPF3RCEFYWWDFGDA/graph.json","fetch_events":"https://pith.science/api/pith-number/F623JQ2RD3CPF3RCEFYWWDFGDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA/action/storage_attestation","attest_author":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA/action/author_attestation","sign_citation":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA/action/citation_signature","submit_replication":"https://pith.science/pith/F623JQ2RD3CPF3RCEFYWWDFGDA/action/replication_record"}},"created_at":"2026-07-05T11:09:33.386471+00:00","updated_at":"2026-07-05T11:09:33.386471+00:00"}